Related papers: Data-Free Model Extraction
Machine learning models are vulnerable to adversarial examples. For the black-box setting, current substitute attacks need pre-trained models to generate adversarial examples. However, pre-trained models are hard to obtain in real-world…
Recent advancements of Deep Neural Networks (DNNs) have seen widespread deployment in multiple security-sensitive domains. The need of resource-intensive training and use of valuable domain-specific training data have made these models a…
The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…
This paper describes a simple, but effective sampling method for optimizing and learning a discrete approximation (or surrogate) of a multi-dimensional function along a one-dimensional line segment of interest. The method does not rely on…
Unlike the white-box counterparts that are widely studied and readily accessible, adversarial examples in black-box settings are generally more Herculean on account of the difficulty of estimating gradients. Many methods achieve the task by…
When deploying pre-trained neural network models in real-world applications, model consumers often encounter resource-constraint platforms such as mobile and smart devices. They typically use the pruning technique to reduce the size and…
For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential malware sample, suspicious email) is deemed…
Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via…
Adversarial robustness poses a critical challenge in the deployment of deep learning models for real-world applications. Traditional approaches to adversarial training and supervised detection rely on prior knowledge of attack types and…
Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…
Modern privacy regulations grant citizens the right to be forgotten by products, services and companies. In case of machine learning (ML) applications, this necessitates deletion of data not only from storage archives but also from ML…
Model stealing (MS) involves querying and observing the output of a machine learning model to steal its capabilities. The quality of queried data is crucial, yet obtaining a large amount of real data for MS is often challenging. Recent…
The study of adversarial vulnerabilities of deep neural networks (DNNs) has progressed rapidly. Existing attacks require either internal access (to the architecture, parameters, or training set of the victim model) or external access (to…
Machine learning systems are often trained using data collected from historical decisions. If past decisions were biased, then automated systems that learn from historical data will also be biased. We propose a black-box approach to…
Analysing the generalisation capabilities of relation extraction (RE) models is crucial for assessing whether they learn robust relational patterns or rely on spurious correlations. Our cross-dataset experiments find that RE models struggle…
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…
Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a…
To launch black-box attacks against a Deep Neural Network (DNN) based Face Recognition (FR) system, one needs to build \textit{substitute} models to simulate the target model, so the adversarial examples discovered from substitute models…
Highly accurate datasets from numerical or physical experiments are often expensive and time-consuming to acquire, posing a significant challenge for applications that require precise evaluations, potentially across multiple scenarios and…
In real case applications within the virtual prototyping process, it is not always possible to reduce the complexity of the physical models and to obtain numerical models which can be solved quickly. Usually, every single numerical…